47,133 repositories indexed
1–24 of 73 · Most stars
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
A privacy-first app that strips AI watermarks from content you own.
Infrastructure for continually self‑improving agents
PRINTFILM: AI short-video marketing and AI short-drama creation platform
An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.
将 SRT 字幕做成暖米黄纸张底的流式笔迹白板手绘动画 skill：mask 分区遮罩编排 + stream 连续笔迹（ink→color）。
Experience-Driven Black-Box Cost Control for Coding Agents
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw
let your agent control your phone
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
Professional agent skills for screenwriting, television writing and dramaturgy
面向抖音直播电商的 Windows 本地 AI Agent Studio，贯通主播发现、直播洞察、直播复盘与短视频内容编导的统一智能工作流。
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)